A Study on Subscriber Value Segmentation and Churn Prediction Based on a Dynamic RFM Model

Sixuan Wang

doi:10.47297/wspciWSP2516-252730.20261004

PDF
Export
Share
Collection
Album

A Study on Subscriber Value Segmentation and Churn Prediction Based on a Dynamic RFM Model

Volume 10, Issue 4

Views: 0 Downloads: 0

A Study on Subscriber Value Segmentation and Churn Prediction Based on a Dynamic RFM Model
A Study on Subscriber Value Segmentation and Churn Prediction Based on a Dynamic RFM Model
School of Economics, Tianjin Normal University, Tianjin, 300387, China
Vol. 10, Issue 4, Pages: 156-159(2026)
Published：30 August 2026
DOI：10.47297/wspciWSP2516-252730.20261004
Accepted：

Scan QR Code

Wang Sixuan.A Study on Subscriber Value Segmentation and Churn Prediction Based on a Dynamic RFM Model[J].Creativity and Innovation,2026,10(04):156-159.
DOI：

Wang Sixuan.A Study on Subscriber Value Segmentation and Churn Prediction Based on a Dynamic RFM Model[J].Creativity and Innovation,2026,10(04):156-159. DOI： 10.47297/wspciWSP2516-252730.20261004.

摘要

Abstract

Developing a dynamic system for user value assessment and churn prediction is crucial for enhancing corporate profitability and social resource allocation. This paper reviews representative literature from three perspectives: the evolution of dynamic value models

mechanisms of churn warning

and socioeconomic effects. First

from an interdisciplinary view combining CRM and machine learning

we define dynamic user value assessment and identify timeliness

multidimensionality

scenario adaptability

and interpretability as key characteristics. Second

following the "data layer—algorithm layer—business layer" logic

we examine construction factors of churn warning. Third

we summarize socioeconomic effects on operational efficiency

user experience

digital industry innovation

and corporate governance. Finally

we discuss subscription-based service characteristics and implementation pathways across different market and cultural contexts. We also identify research gaps and future directions.

关键词

Keywords

references

Xing, S. Y., Zhu, X. F. (2022) An empirical study on user churn prediction in paid knowledge live streaming. Journal of Information Resource Management, 12(04): 121-130+140.

Zhou, W. T., Zhao, Z. J., Liu, Y., Wang, J. Y., Han, X. W. (2022) A study on DBN prediction models for e-commerce customer churn. Computer Engineering and Applications, 58(11): 84-92.

Zhu, F., Wang, Y. Q. (2021) A study on user information clustering and prediction based on k-means and neural network machine learning algorithms. Information Science, 39(07): 83-90.

Zhang, B., Peng, Q. Y. (2018) A study on customer churn prediction based on railway freight value classification. Journal of Railway Science and Engineering, 15(04): 1059-1066.

Xiong, H. X., Zhan, X. M., Li, J. Q., Xiao, B. (2025) A study on the identification of core users in online health communities based on user value segmentation. Journal of Information Science, 43(01): 137-146.

Wei, L., Guo, X. Y. (2020) MOOC user churn prediction based on improved RFM and GMDH algorithms. Chinese Distance Education, (09): 39-43+61+76-77.

Li, X. L., Wang, L. P., Bai, Y., Li, M. L. (2024) Uncovering the value of free users on B2B e-commerce platforms: A study on the dynamic network effects of free users on paying users. Journal of Management Science, 27(07): 19-33.

Xue, Y., Li, G. H., Wu, W. J., Hong, Y. F., Zhou, X. M. (2017) A loyalty-based method for social network user discovery. Computer Applications, 37(11): 3095-3100.

Hu, X. X., Zhao, S. Z., Zhang, G. Z. (2016) A dynamic rough clustering algorithm for contract-based customer segmentation. Small and Micro Computer Systems, 37(10): 2285-2290.

Wu, J., Shi, L., Yang, L., Niu, X., Li, Y., Cui, X., Tsai, S. B., Zhang, Y. (2021) User value identification based on improved RFM model and K-means++ algorithm for complex data analysis. Wireless Communications and Mobile Computing, 2021: Article ID 8884227.

Hughes, A. M. (1994) Strategic Database Marketing. Probus Publishing Company, Chicago.

Ye, Q., Lu, T., Yan, X. B., Li, Y. J. (2006) A study on dynamic customer segmentation methods in customer relationship management. Journal of Management Science, (02): 44-52.

Yan, C. S., Li, Y. J. (2007) A study on a dynamic customer segmentation classification model based on a cloud model. Journal of Harbin Institute of Technology, (02): 299-302.

Lin, J. Y., Wang, Y. (2017) Patient capital and economic development. In: World Bank Economic Review (forthcoming). World Bank, Washington D.C.

Tian, L., Wang, X. H., Ao, J. H. (2008) A study on customer segmentation in e-commerce. Jiangsu Business Review, (07): 52-53.

Sun, J. J., Li, Y. J. (2022) A study on the identification of high-value hot topics based on keyword value segmentation. Journal of Information Science, 41(02): 118-129.

Reyimjiang, K., Sun, Z., Zhao, H., Wang, Z. S. (2018) A study on customer lifetime value classification based on a model incorporating heterogeneous customer data elements: A case study of online sales data for Korla pears. Science and Technology for Development, 14(10): 943-950.

Yan, C., Liu, L. (2020) A study on non-life insurance customer segmentation based on an improved SOM neural network model and the RFM model. Data Analysis and Knowledge Discovery, 4(04): 83-90.

Xie, P. S., Zhang, K., Fan, H. J., Gui, X. Q., Zhang, E. Z. (2019) Research on TFM customer segmentation models and methods for automobile 4S stores. Small and Micro Computer Systems, 40(10): 2165-2169.

Li, P., Yu, X. Y., Sun, B. Y. (2014) A study on video recommendation methods based on user group behavior analysis. Journal of Electronics & Information Technology, 36(06): 1485-1491.